Nightmarish cereal boxes show the limits of AI image generators

An AI-generated image of a cereal box on a gradient background
(Image credit: ThomasDotCodes on YouTube)

Text-to-image AI art generators have been the most radical and controversial development in art and design this year. The technology has exploded at a pace that's hard to keep up with, allowing users to create incredibly realistic images from just a simple text prompt. Sometimes.

Despite the vertiginous technological advances, there are still some requests that seem to fry AI image synths' brains. For anyone wanting to confuse an AI model and make it produce a nightmarish jumble of nonsensical chaos, one creative has found the ultimate silver bullet rubbed in garlic. This video shows one model's attempt to generate images of cereal boxes, and it's quite an experience (if you're not yet up to speed on how the tech works, see our piece on how to use DALL-E 2).

Thank you for reading 5 articles this month* Join now for unlimited access

Enjoy your first month for just £1 / $1 / €1

*Read 5 free articles per month without a subscription

Join now for unlimited access

Try first month for just £1 / $1 / €1

Joseph Foley

Joe is a regular freelance journalist and editor at Creative Bloq. He writes news, features and buying guides and keeps track of the best equipment for creatives, from monitors to accessories and office supplies. A veteran news writer and photographer, he now works as a project manager at the London and Buenos Aires-based design, production and branding agency Hermana Creatives, where he manages a team of designers, photographers and video editors who specialise in producing visual content and collaterals for the hospitality sector. He also dances Argentine tango.